{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.014724829744156084, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0029449659488312166, "grad_norm": 7.919971466064453, "learning_rate": 1e-05, "loss": 14.7502, "step": 1 }, { "epoch": 0.0029449659488312166, "eval_loss": 14.973749160766602, "eval_runtime": 162.2011, "eval_samples_per_second": 3.526, "eval_steps_per_second": 1.763, "step": 1 }, { "epoch": 0.005889931897662433, "grad_norm": 7.999394416809082, "learning_rate": 2e-05, "loss": 14.7952, "step": 2 }, { "epoch": 0.005889931897662433, "eval_loss": 14.773130416870117, "eval_runtime": 27.5556, "eval_samples_per_second": 20.758, "eval_steps_per_second": 10.379, "step": 2 }, { "epoch": 0.00883489784649365, "grad_norm": 7.654147624969482, "learning_rate": 3e-05, "loss": 14.8087, "step": 3 }, { "epoch": 0.011779863795324867, "grad_norm": 8.613886833190918, "learning_rate": 4e-05, "loss": 14.5009, "step": 4 }, { "epoch": 0.011779863795324867, "eval_loss": 14.45578670501709, "eval_runtime": 27.5528, "eval_samples_per_second": 20.76, "eval_steps_per_second": 10.38, "step": 4 }, { "epoch": 0.014724829744156084, "grad_norm": 9.626219749450684, "learning_rate": 5e-05, "loss": 14.6117, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3699128496291840.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }